metadata
license: apache-2.0
base_model: t5-base
tags:
- text2text-generation
- generated_from_trainer
metrics:
- sacrebleu
model-index:
- name: vi-correction-t5
results: []
vi-correction-t5
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1465
- Sacrebleu: 0.4788
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|---|---|---|---|---|
| No log | 0.992 | 93 | 0.1898 | 0.1884 |
| No log | 1.9947 | 187 | 0.1586 | 0.4429 |
| No log | 2.9973 | 281 | 0.1491 | 0.4715 |
| No log | 3.968 | 372 | 0.1465 | 0.4788 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1